Time series clustering with an EM algorithm for mixtures of linear Gaussian state space models. (June 2023)

• Record Type: Journal Article
• Authors: Umatani, Ryohei; Imai, Takashi; Kawamoto, Kaoru; Kunimasa, Shutaro
• Is Part Of: Pattern recognition. Volume 138(2023)
• Publication Date: 2023-06
• Subjects: Time series clustering -- Model-based clustering -- State space model -- EM algorithm -- Mixture model; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2023.109375
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a time series clustering method based on mixtures of state space models. Our method performs clustering while modeling each cluster with a state space model. Our method incorporates a new EM algorithm for mixtures of state space models. Experiments showed our method is effective in clustering non-stationary time series. Abstract: In this paper, we consider the task of clustering a set of individual time series while modeling each cluster, that is, model-based time series clustering. The task requires a parametric model with sufficient flexibility to describe the dynamics in various time series. To address this problem, we propose a novel model-based time series clustering method with mixtures of linear Gaussian state space models, which have high flexibility. The proposed method uses a new expectation-maximization algorithm for the mixture model to estimate the model parameters, and determines the number of clusters using the Bayesian information criterion. Experiments on a simulated dataset demonstrate the effectiveness of the method in clustering, parameter estimation, and model selection. The method is applied to real datasets commonly used to evaluate time series clustering methods. Results showed that the proposed method produces clustering results that are as accurate or more accurate than those obtained using previous methods.